Bit flipping can be used as a postprocessing technique to further improv...
The recent advances of compressing high-accuracy convolution neural netw...
Due to the powerful ability to encode image details and semantics, many
...
Object detection often costs a considerable amount of computation to get...
Unsupervised domain adaptation enables intelligent models to transfer
kn...
As a more practical setting for unsupervised domain adaptation, Universa...
Multi-branch is extensively studied for learning rich feature representa...
Domain alignment (DA) has been widely used in unsupervised domain adapta...
Exploring contextual information in convolution neural networks (CNNs) h...
A big challenge of person re-identification (Re-ID) using a multi-branch...
Entropy minimization has been widely used in unsupervised domain adaptat...
Learning diverse features is key to the success of person re-identificat...
This paper introduces a lightweight convolutional neural network, called...
The recent years have witnessed great advances for semantic segmentation...
The extensive computational burden limits the usage of CNNs in mobile de...
Capsules as well as dynamic routing between them are most recently propo...